Triple

T6389025
Position Surface form Disambiguated ID Type / Status
Subject Waimakariri District E143771 entity
Predicate containsSettlement P847 FINISHED
Object Cust
Cust is a small rural township in New Zealand’s Canterbury region, known for its agricultural surroundings and close-knit community.
E589775 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Cust | Statement: [Waimakariri District, containsSettlement, Cust]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cust
Context triple: [Waimakariri District, containsSettlement, Cust]
  • A. COS
    COS is the French Armed Forces' elite joint command responsible for planning and conducting special operations.
  • B. COS
    COS is a Hubble Space Telescope instrument designed to study the origins and evolution of the universe by analyzing the ultraviolet light from distant astronomical objects.
  • C. COS
    COS is the College of Science at Northeastern University, encompassing disciplines such as biology, chemistry, physics, mathematics, and related scientific fields.
  • D. CST
    CST is the time zone used throughout mainland China, eight hours ahead of Coordinated Universal Time (UTC+8).
  • E. CST
    CST is a prominent Chicago-based theater company renowned for its innovative productions of Shakespearean and other classic and contemporary works.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cust
Triple: [Waimakariri District, containsSettlement, Cust]
Generated description
Cust is a small rural township in New Zealand’s Canterbury region, known for its agricultural surroundings and close-knit community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cust
Target entity description: Cust is a small rural township in New Zealand’s Canterbury region, known for its agricultural surroundings and close-knit community.
  • A. COS
    COS is the French Armed Forces' elite joint command responsible for planning and conducting special operations.
  • B. COS
    COS is the College of Science at Northeastern University, encompassing disciplines such as biology, chemistry, physics, mathematics, and related scientific fields.
  • C. COS
    COS is a Hubble Space Telescope instrument designed to study the origins and evolution of the universe by analyzing the ultraviolet light from distant astronomical objects.
  • D. CST
    CST is the abbreviation for the Communications Security Establishment, Canada’s national cryptologic agency responsible for foreign signals intelligence and cybersecurity.
  • E. CST
    CST is the National Rail station code for London Cannon Street railway station in central London.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c008dac1ec81909cef8157ccd69962 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0686b4f34819088ff07185b34e536 completed March 22, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6388224fc8190aabd6e6d75887367 completed March 27, 2026, 7:57 a.m.
NEDg Description generation batch_69c6397756c481909ca13339c2186c0a completed March 27, 2026, 8:01 a.m.
NED2 Entity disambiguation (via description) batch_69c63a0a4a108190b474555d8cb1540c completed March 27, 2026, 8:04 a.m.
Created at: March 22, 2026, 4:34 p.m.